Title :
Hourly Traffic Forecasts Using Interacting Multiple Model (IMM) Predictor
Author_Institution :
Shanghai Municipal Transp. Inf. Center, Shanghai Urban & Rural Constr. & Transp. Comm., Shanghai, China
Abstract :
Accurate and timely forecasting of traffic status is crucial to effective management of intelligent transportation systems (ITS). An interacting multiple model (IMM) predictor is proposed to forecast travel time index (TTI) data in the letter. To the best of our knowledge, it is the first time to propose the novel combined predictor. Seven baseline individual predictors are selected as combination components because of their proved effectiveness. Experimental results demonstrate that the IMM predictor can significantly outperform the other predictors and provide a large improvement in stability and robustness. This reveals that the approach is practically promising in traffic forecasting.
Keywords :
forecasting theory; traffic; hourly traffic forecast; intelligent transportation system; interacting multiple model predictor; traffic forecasting; traffic status; travel time index data; Autoregressive processes; Computational modeling; Forecasting; Hidden Markov models; Markov processes; Prediction algorithms; Predictive models; Interacting multiple model (IMM); traffic forecasting; travel time index (TTI);
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2011.2165537
